IoT MONITORING OF HERDS AND THE HERDSMEN

Igba Priscillia Uzoamaka

System Administrator, ICT Directorate, University of Jos, Nigeria.

5/10/2018 1

Background Research

In recent times, there has been a scourge of attacks on farmers, their farmland, produce and villagers by herdsmen in and around the middle-belt region of Nigeria. As a result of the vast land and sparse population in the rural communities and villages, the herdsmen find it less difficult to attack the farmers and villagers.

https://www.myknowledgeresources.com/2018/01/13/nigeria-verges-

genocide-amid-new-wave-brazen-attacks-fulani-herdsmen/

5/10/2018 2

EXISTING SITUATION

5/10/2018 3

Objectives To use IoT to mitigate these attacks by Fulani

herdsmen on some rural communities over grazing areas in Middle-belt, Nigeria.

5/10/2018 4

Proposed Actions

To install Passive Infrared(PIR) motion sensors to detect body heat within the location within a particular time.

To install an alarm sensor that triggers an alarm when motion is detected.

To use an outdoor wireless device to build a point to point backhaul network for the LoRaWan Gateway.

5/10/2018 5

Proposed framework

User

Server

Border with PIR sensors

Village community

Lora Gateway

5/10/2018 6

5/10/2018 7

Questions/ Pointers?

Traffic Generator for LoRa Networks

Anjali R. Askhedkar & Nilam M. PradhanSupervisor : Dr. Bharat S. ChaudhariMIT World Peace UniversityPune, India

MOTIVATION

•Possibility of a high density of LoRa devices simultaneously active in the same cell

•Difficulty in study of high density IoT scenario in real test beds

•Analyze the response of wireless networks with the increase in capacity

•Scalability of LoRaWAN is under investigation

•To test different network planning solutions for LoRa networks

OBJECTIVE•To implement a LoRa cell traffic generator that emulates the behaviour of

multiple LoRa sensor nodes in the same cell by using software defined radio

platform (USRP) and LoRa gateway

•Analyze the cell level performance of a LoRa network under different spreading

factors

METHODOLOGY•System can be considered as a simple superposition of independentSubsystems(single channel, single spreading factor)

•Use multiple transmission channels and spreading factors to generate acombined signal

•Implementation of traffic generator using USRP SDR platform and LoRagateway

•Scheduling of signals to be transmitted in real time according to required trafficand cell scenario

EMULATOR ARCHITECTURE))))))USRP LORA

GATEWAY

TRAFFIC GENERATOR

STATISTICS COLLECTOR

))))))))))))))))))))))

VIRTUAL GATEWAY

NODES

SOFTWARE MODULE

HARDWARE MODULE

IMPLEMENTATION

•Hardware: Ettus B200 USRP,

LoRa Gateway

•Software : GNU Radio,

Python

LoRa Communication using USRP

LoRa Communication using USRP

REFERENCES•Michelle Gucciardo, Illinea Tinnirello, Dominico Garlessi “ Demo: A cell leveltraffic generator for LoRa Networks ”, MobiCom’17, October 16-20, 2017

•Matthew Knight, Balint Seeber, ”Decoding LoRa: Realizing a Modern LPWANwith SDR”

•www.semtech.com/technology/lora•www.rtl-sdr.com/decoding-the-iot-lora-protocol-with-an-rtl-sdr/

Thank You !

RADIATION MONITORING IN NICARAGUA

Edith Villegas

Why measure radon?

■ Naturally present everywhere in the environment

■ Second leading cause of lung cancer worldwide

■ Approximately half the radiation dose to the general

population comes from radon

■ Can be correlated to seismic activity

Radon Measurements

■ Done in Masaya Volcano, in Nicaragua, and nearby

houses

■ Measurements found to be below acceptable limits

■ More data points needed

■ Plans to continue monitoring in mines

Ref: Measurements of 222Rn in localized Areas of

Masaya Volcano, Nicaragua using E-PERM detectors

Meza J1, Roas N2

Radon detectors used

Why measure natural background radiation?

■ Ionizing Radiation is present everywhere

■ To assess the radiation dose naturally received by

the population

■ To know your environment and detect changes in it

Detectors used

■ Thermoluminescent Detectors

■ LiF:Mg,Cu,P material (more sensitivity)

■ Passive detectors

Workplace monitoring

■ Monitoring of 6 border posts in the country, using

TLDs

■ Detects radiation from high energy x-ray machine

■ Detects sources going by

Ref: Evaluacion de dosimetria ambiental en 6 puestos fronterizos de nicaragua

utilizando dosimetros termoluminiscentes. Norma Roas, Fredy Somarriba

Background Monitoring

Implementing IoT

■ Automatization of the process

■ More data points in time (at least twice a day)

■ Data immediately available

Detector Characteristics

Background Measurement:

■ High sensitivity for lower dose rates (~50nSv/h)

Workplace monitoring

■ Medium sensitivity for low doses, wide range

Calibration of detectors

■ Calibration of gamma detectors using 137Cs source

■ Calibration of radon detectors by intercomparison (in

a sealed chamber with a radon source)

Expected Outcomes

■ Real time monitoring for workplaces

■ More data points on radiation across the country

■ More data points on radon, more frequently spaced

■ In places where it can be correlated to seismic and

volcanic activity

Thanks!

1Greyner Vanegas Néstor Traña Abraham Ampie

2

3

4

5(OMS/UNICEF, 2017)

6(OMS/UNICEF, 2017)

7(OMS/UNICEF, 2017)

8ASHRAE, ASHRAE/ASHE STANDARD 170-2008, 1791 Tullie Circle NE. Atlanta, 2008.

9

10

11

12

13

14

15

16

17

18

19

20

21

22

0

10

20

30

40

50

60

Sensores de temperatura y humedad

Sensor de Temperatura Rojo (ºC) Sensor de temperatura Negro (ºC)

Sensor de Temperatura CPF (ºC) Sensor de humedad Rojo (%)

Sensor de humedad Negro (%)

40

42

44

46

48

50

52

54

13

:00

14

:00

15

:00

16

:00

17

:00

18

:00

19

:00

20

:00

21

:00

22

:00

23

:00

0:0

0

1:0

0

2:0

0

3:0

0

4:0

0

5:0

0

6:0

0

7:0

0

8:0

0

9:0

0

10

:00

11

:00

12

:00

Nivel de ruido (dB)

350

355

360

365

370

375

Sensor de luminocidad (Lux)

23

CASE STUDY FOR BESHELO BASIN

PHD RESEARCH CONCEPT

1

IoT based soil monitoring and crop management Intelligent

System using Machine Learning algorithms

Outline 2

Introduction

Research Problem

Objective

Conceptual Framework

Research Impact

Introduction 3

Agriculture is the pillar for the economical dev’t of

Ethiopia

It is also main source of food for the country

However, food insecurity is a concern in Sub-Saharan

Africa, including Ethiopia

Traditional agricultural practices, climate change and

unavailability of abundant, well-organized information

are some factors affecting agricultural productivity

Introduction 4

Collection and analysis of crop production impacting

parameters can help generate useful information

The presentation and analysis of trends of a

particular location can also help in risk prediction

and disaster management

Fertilizer and pest usage can be effective if supported

with necessary attributes

Introduction 5

ICT can be a wayout

In countries like Ethiopia with:

Limited Network infrastructure

Exagurated hardware & software cost

High illiteracy rate

Usable, cost-effective yet efficient ICT systems shall

be produced

Research Problem 6

How can environmental and soil parameters

that affect crop yield and productivity of

agriculture be collected using IoT?

How to use GIS, DIP and ML techniques to

analyze collected data?

How can agricultural disasters be prevented

thru smart systems?

General Objective 7

The general objective of the research is to design an

IoT based soil PH, soil moisture and soil Nitrogen

level data collection system and analyze the collected

data through GIS and Image processing techniques

and predict crop yields and other valuable

information using machine learning algorithm

Specific Objectives 8

Model environmental and soil factors affecting crop yield

Model topography of the target location using GIS

Design an efficient network of IoT so as devices to server communication can be achieved with minimal cost and low power requirment

Implemenet and deploy sensors to collect target parameters from the field

Capture leaf or stem images of crops from close proximity using either drones or digital cameras.

Collect and analyse relevant GIS data

Specific Objectives 9

Design an algorithm to construct a knowledgebase of the system

Analyse the captured images using DIP techniques to determine the soil’s N level

Process data collected from sensors using GIS tool

Design an enference engine using machine learning algorithm which generates new information from processed data

Integrate the aforementioned components and construct a system that can predict yield improving situations

Conceptual Framework 10

Outcome and Research Impact 11

Gathering and systematical storage of environmental

and soil parameters in real-time

Prediction of crop yield improving and disaster

prevention data

Design expert model and efficient IoT network

architecture for agriculture

12

Thank you

Questions/Comments/Feedbacks???